From c3ade74e23bb49da8cee399e6ff3c64e4442311f Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 11 Aug 2020 18:30:40 -0700 Subject: [PATCH 2380/2944] mm/vmscan: protect the workingset on anonymous LRU task #30476868 commit b518154e59aab3ad0780a169c5cc84bd4ee4357e upstream In current implementation, newly created or swap-in anonymous page is started on active list. Growing active list results in rebalancing active/inactive list so old pages on active list are demoted to inactive list. Hence, the page on active list isn't protected at all. Following is an example of this situation. Assume that 50 hot pages on active list. Numbers denote the number of pages on active/inactive list (active | inactive). 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(uo) | 50(h) 3. workload: another 50 newly created (used-once) pages 50(uo) | 50(uo), swap-out 50(h) This patch tries to fix this issue. Like as file LRU, newly created or swap-in anonymous pages will be inserted to the inactive list. They are promoted to active list if enough reference happens. This simple modification changes the above example as following. 1. 50 hot pages on active list 50(h) | 0 2. workload: 50 newly created (used-once) pages 50(h) | 50(uo) 3. workload: another 50 newly created (used-once) pages 50(h) | 50(uo), swap-out 50(uo) As you can see, hot pages on active list would be protected. Note that, this implementation has a drawback that the page cannot be promoted and will be swapped-out if re-access interval is greater than the size of inactive list but less than the size of total(active+inactive). To solve this potential issue, following patch will apply workingset detection similar to the one that's already applied to file LRU. Signed-off-by: Joonsoo Kim Signed-off-by: Andrew Morton Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Link: http://lkml.kernel.org/r/1595490560-15117-3-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Linus Torvalds Signed-off-by: zhongjiang-ali Reviewed-by: Xunlei Pang --- include/linux/swap.h | 2 +- kernel/events/uprobes.c | 2 +- mm/huge_memory.c | 6 +++--- mm/khugepaged.c | 2 +- mm/memory.c | 9 ++++----- mm/migrate.c | 2 +- mm/swap.c | 13 +++++++------ mm/swapfile.c | 2 +- mm/userfaultfd.c | 2 +- mm/vmscan.c | 4 +--- 10 files changed, 21 insertions(+), 23 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index 1ccb7a1..f9a4137 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -350,7 +350,7 @@ extern void lru_add_page_tail(struct page *page, struct page *page_tail, extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); -extern void lru_cache_add_active_or_unevictable(struct page *page, +extern void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma); /* linux/mm/vmscan.c */ diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 9610c6c..de4ce1b 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -182,7 +182,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, get_page(new_page); page_add_new_anon_rmap(new_page, vma, addr, false); - lru_cache_add_active_or_unevictable(new_page, vma); + lru_cache_add_inactive_or_unevictable(new_page, vma); if (!PageAnon(old_page)) { dec_mm_counter(mm, mm_counter_file(old_page)); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cd69bd5..3de3b84 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -641,7 +641,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr, true); - lru_cache_add_active_or_unevictable(page, vma); + lru_cache_add_inactive_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); @@ -1329,7 +1329,7 @@ static vm_fault_t do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, entry = mk_pte(pages[i], vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); page_add_new_anon_rmap(pages[i], vmf->vma, haddr, false); - lru_cache_add_active_or_unevictable(pages[i], vma); + lru_cache_add_inactive_or_unevictable(pages[i], vma); vmf->pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte_none(*vmf->pte)); set_pte_at(vma->vm_mm, haddr, vmf->pte, entry); @@ -1478,7 +1478,7 @@ static vm_fault_t do_huge_pmd_wp_page_slow(struct vm_fault *vmf, pmd_t orig_pmd) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd); page_add_new_anon_rmap(new_page, vma, haddr, true); - lru_cache_add_active_or_unevictable(new_page, vma); + lru_cache_add_inactive_or_unevictable(new_page, vma); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); if (!page) { diff --git a/mm/khugepaged.c b/mm/khugepaged.c index d1f5fab..adc964d 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1163,7 +1163,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); - lru_cache_add_active_or_unevictable(new_page, vma); + lru_cache_add_inactive_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); diff --git a/mm/memory.c b/mm/memory.c index 7e6107b..d9c8057 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2564,7 +2564,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); - lru_cache_add_active_or_unevictable(new_page, vma); + lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the @@ -3093,10 +3093,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); - lru_cache_add_active_or_unevictable(page, vma); + lru_cache_add_inactive_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); - activate_page(page); } swap_free(entry); @@ -3236,7 +3235,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - lru_cache_add_active_or_unevictable(page, vma); + lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3504,7 +3503,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); - lru_cache_add_active_or_unevictable(page, vma); + lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); diff --git a/mm/migrate.c b/mm/migrate.c index c9e95e0..fc345ae 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2704,7 +2704,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, inc_mm_counter(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, addr, false); if (!is_zone_device_page(page)) - lru_cache_add_active_or_unevictable(page, vma); + lru_cache_add_inactive_or_unevictable(page, vma); get_page(page); if (flush) { diff --git a/mm/swap.c b/mm/swap.c index 4bb48ba..b2edd72 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -445,23 +445,24 @@ void lru_cache_add(struct page *page) EXPORT_SYMBOL(lru_cache_add); /** - * lru_cache_add_active_or_unevictable + * lru_cache_add_inactive_or_unevictable * @page: the page to be added to LRU * @vma: vma in which page is mapped for determining reclaimability * - * Place @page on the active or unevictable LRU list, depending on its + * Place @page on the inactive or unevictable LRU list, depending on its * evictability. Note that if the page is not evictable, it goes * directly back onto it's zone's unevictable list, it does NOT use a * per cpu pagevec. */ -void lru_cache_add_active_or_unevictable(struct page *page, +void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { + bool unevictable; + VM_BUG_ON_PAGE(PageLRU(page), page); - if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) - SetPageActive(page); - else if (!TestSetPageMlocked(page)) { + unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; + if (unlikely(unevictable) && !TestSetPageMlocked(page)) { /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte diff --git a/mm/swapfile.c b/mm/swapfile.c index 81d8126..2ec6608 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1863,7 +1863,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, page_add_anon_rmap(page, vma, addr, false); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); - lru_cache_add_active_or_unevictable(page, vma); + lru_cache_add_inactive_or_unevictable(page, vma); } swap_free(entry); /* diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 48ebde4..8db7183 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -90,7 +90,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, inc_mm_counter(dst_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); - lru_cache_add_active_or_unevictable(page, dst_vma); + lru_cache_add_inactive_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); diff --git a/mm/vmscan.c b/mm/vmscan.c index 2ea40b7..1031650 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1006,8 +1006,6 @@ static enum page_references page_check_references(struct page *page, return PAGEREF_RECLAIM; if (referenced_ptes) { - if (PageSwapBacked(page)) - return PAGEREF_ACTIVATE; /* * All mapped pages start out with page table * references from the instantiating fault, so we need @@ -1030,7 +1028,7 @@ static enum page_references page_check_references(struct page *page, /* * Activate file-backed executable pages after first usage. */ - if (vm_flags & VM_EXEC) + if ((vm_flags & VM_EXEC) && !PageSwapBacked(page)) return PAGEREF_ACTIVATE; return PAGEREF_KEEP; -- 1.8.3.1